Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    anti

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     OMIT
    -0.07
     revis
    -0.07
     controls
    -0.07
     nons
    -0.06
     Controls
    -0.06
     『
    -0.06
     DOES
    -0.06
     мног
    -0.06
    _KIND
    -0.06
     caches
    -0.06
    POSITIVE LOGITS
    िवर
    0.07
    原因
    0.06
    yar
    0.06
    /Game
    0.06
    	
↵	
↵
    0.06
     webcam
    0.06
    abi
    0.06
    ислов
    0.06
     firewall
    0.06
    Angel
    0.06
    Act Density 0.000%

    No Known Activations